在 Java 中加载 sklearn 模型。在 python 中使用 DNNClassifier 创建的模型

Question

目标是在 Java 中使用tensorflow.contrib.learn.learn.DNNClassifier 打开一个在 python 中创建/训练的模型。

目前的主要问题是知道“张量”的名称，以便在 java 中的 session runner 方法中给出。

我在 python 中有这个测试代码：

    from __future__ import division, print_function, absolute_import
import tensorflow as tf
import pandas as pd
import tensorflow.contrib.learn as learn
import numpy as np
from sklearn import metrics
from sklearn.cross_validation import train_test_split
from tensorflow.contrib import layers
from tensorflow.contrib.learn.python.learn.utils import input_fn_utils
from tensorflow.python.ops import array_ops
from tensorflow.python.framework import dtypes
from tensorflow.python.util.compat import as_text

print(tf.VERSION)

df = pd.read_csv('../NNNormalizeData-out.csv')

inputs = []
target = []

y=0;    
for x in df.columns:
    if y != 35 :
        #print("added %d" %y)
        inputs.append(x)
    else :
        target.append(x)
    y+=1

total_inputs,total_output = df.as_matrix(inputs).astype(np.float32),df.as_matrix([target]).astype(np.int32)

train_inputs, test_inputs, train_output, test_output = train_test_split(total_inputs, total_output, test_size=0.2, random_state=42)

feature_columns = [tf.contrib.layers.real_valued_column("", dimension=train_inputs.shape[1],dtype=tf.float32)]
#target_column = [tf.contrib.layers.real_valued_column("output", dimension=train_output.shape[1])]

classifier = learn.DNNClassifier(hidden_units=[10, 20, 5], n_classes=5
                                 ,feature_columns=feature_columns)

classifier.fit(train_inputs, train_output, steps=100)

#Save Model into saved_model.pbtxt file (possible to Load in Java)
tfrecord_serving_input_fn = tf.contrib.learn.build_parsing_serving_input_fn(layers.create_feature_spec_for_parsing(feature_columns))  
classifier.export_savedmodel(export_dir_base="test", serving_input_fn = tfrecord_serving_input_fn,as_text=True)


# Measure accuracy
pred = list(classifier.predict(test_inputs, as_iterable=True))
score = metrics.accuracy_score(test_output, pred)
print("Final score: {}".format(score))

# test individual samples 
sample_1 = np.array( [[0.37671986791414125,0.28395908337619136,-0.0966095873607713,-1.0,0.06891621389763203,-0.09716678086712205,0.726029084013637,4.984689881073479E-4,-0.30296253267499107,-0.16192917054985334,0.04820256230479658,0.4951319883569152,0.5269983894210499,-0.2560313828048315,-0.3710980821053321,-0.4845867212612598,-0.8647234314469595,-0.6491591208322198,-1.0,-0.5004549422844073,-0.9880910165770813,0.5540293108747256,0.5625990251930839,0.7420121698556554,0.5445551415657979,0.4644276850235627,0.7316976292340245,0.636690006814346,0.16486621649984112,-0.0466018967678159,0.5261100063227044,0.6256168612312738,-0.544295484930702,0.379125782517193,0.6959368575211544]], dtype=float)
sample_2 = np.array( [[1.0,0.7982741870963959,1.0,-0.46270838239235024,0.040320274521029376,0.443451913224413,-1.0,1.0,1.0,-1.0,0.36689718911339564,-0.13577379160035796,-0.5162916256414466,-0.03373651520104648,1.0,1.0,1.0,1.0,0.786999801054777,-0.43856035121103853,-0.8199093927945158,1.0,-1.0,-1.0,-0.1134921695894473,-1.0,0.6420892436196663,0.7871737734493178,1.0,0.6501788845358409,1.0,1.0,1.0,-0.17586627413625022,0.8817194210401085]], dtype=float)

pred = list(classifier.predict(sample_2, as_iterable=True))
print("Prediction for sample_1 is:{} ".format(pred))

pred = list(classifier.predict_proba(sample_2, as_iterable=True))
print("Prediction for sample_2 is:{} ".format(pred))

创建了一个 model_saved.pbtxt 文件。

我尝试使用以下代码在 Java 中加载此模型：

    public class HelloTF {
    public static void main(String[] args) throws Exception {
        SavedModelBundle bundle=SavedModelBundle.load("/java/workspace/APIJavaSampleCode/tfModels/dnn/ModelSave","serve");
        Session s = bundle.session();

        double[] inputDouble = {1.0,0.7982741870963959,1.0,-0.46270838239235024,0.040320274521029376,0.443451913224413,-1.0,1.0,1.0,-1.0,0.36689718911339564,-0.13577379160035796,-0.5162916256414466,-0.03373651520104648,1.0,1.0,1.0,1.0,0.786999801054777,-0.43856035121103853,-0.8199093927945158,1.0,-1.0,-1.0,-0.1134921695894473,-1.0,0.6420892436196663,0.7871737734493178,1.0,0.6501788845358409,1.0,1.0,1.0,-0.17586627413625022,0.8817194210401085};
        float [] inputfloat=new float[inputDouble.length];
        for(int i=0;i<inputfloat.length;i++)
        {
            inputfloat[i]=(float)inputDouble[i];
        }
        Tensor inputTensor = Tensor.create(new long[] {35}, FloatBuffer.wrap(inputfloat) );

        Tensor result = s.runner()
                .feed("input_example_tensor", inputTensor)
                .fetch("dnn/multi_class_head/predictions/probabilities")
                .run().get(0);


         float[] m = new float[5];
         float[] vector = result.copyTo(m);
         float maxVal = 0;
         int inc = 0;
         int predict = -1;
         for(float val : vector) 
         {
             System.out.println(val+"  ");
             if(val > maxVal) {
                 predict = inc;
                 maxVal = val;
             }
             inc++;
         }
         System.out.println(predict);



    }
} 

我在 .run().get(0); 上遇到错误；行：

Exception in thread "main" org.tensorflow.TensorFlowException: Output 0 of type float does not match declared output type string for node _recv_input_example_tensor_0 = _Recv[_output_shapes=[[-1]], client_terminated=true, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=3663984897684684554, tensor_name="input_example_tensor:0", tensor_type=DT_STRING, _device="/job:localhost/replica:0/task:0/cpu:0"]()
    at org.tensorflow.Session.run(Native Method)
    at org.tensorflow.Session.access$100(Session.java:48)
    at org.tensorflow.Session$Runner.runHelper(Session.java:285)
    at org.tensorflow.Session$Runner.run(Session.java:235)
    at tensorflow.HelloTF.main(HelloTF.java:35)

Answer 1

好的，我终于解决了：主要问题是在 java 中使用的输入名称是“dnn/input_from_feature_columns/input_from_feature_columns/concat”而不是“input_example_tensor”。

我使用图形导航发现了这一点：tensorboard --logdir=D:\python\Workspace\Autoencoder\src\dnn\ModelSave

这里是java代码：

public class HelloTF {
public static void main(String[] args) throws Exception {
    SavedModelBundle bundle=SavedModelBundle.load("/java/workspace/APIJavaSampleCode/tfModels/dnn/ModelSave","serve");
    Session s = bundle.session();

    double[] inputDouble = {1.0,0.7982741870963959,1.0,-0.46270838239235024,0.040320274521029376,0.443451913224413,-1.0,1.0,1.0,-1.0,0.36689718911339564,-0.13577379160035796,-0.5162916256414466,-0.03373651520104648,1.0,1.0,1.0,1.0,0.786999801054777,-0.43856035121103853,-0.8199093927945158,1.0,-1.0,-1.0,-0.1134921695894473,-1.0,0.6420892436196663,0.7871737734493178,1.0,0.6501788845358409,1.0,1.0,1.0,-0.17586627413625022,0.8817194210401085};
    float [] inputfloat=new float[inputDouble.length];
    for(int i=0;i<inputfloat.length;i++)
    {
        inputfloat[i]=(float)inputDouble[i];
    }
FloatBuffer.wrap(inputfloat) );
    float[][] data= new float[1][35];
    data[0]=inputfloat;
    Tensor inputTensor=Tensor.create(data);


    Tensor result = s.runner()
            .feed("dnn/input_from_feature_columns/input_from_feature_columns/concat", inputTensor)
            //.feed("input_example_tensor", inputTensor)
            //.fetch("tensorflow/serving/classify")
            .fetch("dnn/multi_class_head/predictions/probabilities")
            //.fetch("dnn/zero_fraction_3/Cast")
            .run().get(0);


     float[][] m = new float[1][5];
     float[][] vector = result.copyTo(m);
     float maxVal = 0;
     int inc = 0;
     int predict = -1;
     for(float val : vector[0]) 
     {
         System.out.println(val+"  ");
         if(val > maxVal) {
             predict = inc;
             maxVal = val;
         }
         inc++;
     }
     System.out.println(predict);



}

}

我已经测试了输出：

植物侧：

Prediction for sample_2 is:[3] 
Prediction for sample_2 is:[array([ 0.17157166,  0.24475774,  0.16158019,  0.24648622,  0.17560424], dtype=float32)] 

Java 端：

0.17157166  
0.24475774  
0.16158019   
0.24648622  
0.17560424  
3

Answer 2

错误消息提供了一个线索：模型中名为 "input_example_tensor" 的张量预期具有 string 内容，而您提供了 float 值。

从张量的名称和你的代码来看，我猜你输入的张量是defined in input_fn_utils.py。这个张量被传递给tf.parse_example() op，它需要一个tf.train.Example 协议缓冲区的向量，序列化为字符串。

Answer 3

在 Tensorflow 1.1 上没有feed("input_example_tensor", inputTensor) 时出现错误。

但我发现example.proto 可以作为“input_example_tensor”输入，尽管花了很多时间来弄清楚如何为序列化协议缓冲区创建字符串张量。

这就是我创建inputTensor的方式。

org.tensorflow.example.Example.Builder example = org.tensorflow.example.Example.newBuilder();   
/* set some features to example... */

Tensor exampleTensor = Tensor.create(example.build().toByteArray());
// Here, the shape of exampleTensor is not specified yet.

// Set the shape to feed this as "input_example_tensor"
Graph g = bundle.graph(); 
Output examplePlaceholder =
                  g.opBuilder("Placeholder", "example")
                  .setAttr("dtype", exampleTensor.dataType())                        
                      .build().output(0);
Tensor shapeTensor = Tensor.create(new long[]{1}, IntBuffer.wrap(new int[]{1}));                      
Output shapeConst = g.opBuilder("Const", "shape")
                      .setAttr("dtype", shapeTensor.dataType())
                      .setAttr("value", shapeTensor)
                      .build().output(0);
Output shaped = g.opBuilder("Reshape", "output").addInput(examplePlaceholder).addInput(shapeConst).build().output(0);


Tensor inputTensor = s.runner().feed(examplePlaceholder, exampleTensor).fetch(shaped).run().get(0);                   
// Now, inputTensor has shape of [1] and ready to feed.     

Answer 4

您在 .feed() 和 .fetch() 中的参数应该与您的输入和输出数据类型匹配。

您可以查看已保存的model.pbtxt 文件。有关于您的参数及其输入/输出类型的详细信息。

例如，

我的java代码

Tensor result = s.runner()
        .feed("ParseExample/ParseExample", inputTensor)
        .fetch("dnn/binary_logistic_head/predictions/probabilities")
        .run().get(0);

我的 savedModel.pbtxt（其中一部分）

node {
  name: "ParseExample/ParseExample"
  op: "ParseExample"
  input: "input_example_tensor"
  input: "ParseExample/ParseExample/names"
  input: "ParseExample/ParseExample/dense_keys_0"
  input: "ParseExample/Const"
  attr {
    key: "Ndense"
    value {
      i: 1
    }
  }
  attr {
    key: "Nsparse"
    value {
      i: 0
    }
  }
  attr {
    key: "Tdense"
    value {
      list {
        type: DT_FLOAT
      }
    }
  }
  attr {
    key: "_output_shapes"
    value {
      list {
        shape {
          dim {
            size: -1
          }
          dim {
            size: 2
          }
        }
      }
    }
  }
  attr {
    key: "dense_shapes"
    value {
      list {
        shape {
          dim {
            size: 2
          }
        }
      }
    }
  }
  attr {
    key: "sparse_types"
    value {
      list {
      }
    }
  }
}
  outputs {
    key: "scores"
    value {
      name: "dnn/binary_logistic_head/predictions/probabilities:0"
      dtype: DT_FLOAT
      tensor_shape {
        dim {
          size: -1
        }
        dim {
          size: 2
        }
      }
    }
  }

它们都与我的数据类型 float 兼容。